Effective urban traffic signal control in large-scale networks remains challenging due to complex interdependencies among intersections and unpredictable fluctuations in traffic conditions. To address these challenges, this paper proposes a novel Adaptive Hybrid Multi-Objective Optimization Algorithm with Reinforcement Learning (AHMOA-RL) for robust and scalable traffic signal management. The core innovation of AHMOA-RL lies in a hierarchical optimization framework that efficiently decomposes the problem into global region-level coordination and local intersection-level refinements, significantly reducing computational complexity while ensuring synchronized control across extensive urban networks. A Q-learning agent dynamically selects among multiple evolutionary operators—Genetic Algorithm, Differential Evolution, Particle Swarm Optimization, and Local Search—to strategically balance exploration and exploitation during optimization. Additionally, a memory-based evaluation mechanism leveraging historical data is integrated to smooth transient traffic anomalies and provide stable performance estimates. Extensive simulations on large-scale city networks inspired by Manhattan, Paris, São Paulo, and Istanbul demonstrate that AHMOA-RL consistently outperforms state-of-the-art methods, achieving substantial reductions in average vehicle delays, improved network stability, and enhanced robustness under diverse traffic conditions. The algorithm’s compact Pareto fronts and superior convergence characteristics validate its effectiveness for practical deployment in complex urban environments.

ABSTRACT This study first clarifies the concept of azimuth localizability and elaborates on the design process of a distributed localization algorithm based on local azimuth measurements, with a specific focus on fixed‐time localization using local azimuth measurements. The proposed method enables each follower node to determine its position in the global coordinate system within a fixed time frame by leveraging local azimuth measurements and network topology constraints. Furthermore, the study investigates the impact of various parameters and initial position estimates on convergence time. Finally, simulation experiments are conducted on the MATLAB platform, encompassing both 2D and 3D fixed‐time localization based on local azimuth measurements.

The integration of renewable energy sources (RES) into new power system (NPS) represents a crucial approach for reducing carbon emissions (CEs) and mitigating resource consumption in cloud computing centers. However, the inherent uncertainties of RES generation, such as randomness, volatility, and intermittency, pose significant challenges to the scheduling of NPS. A data-driven multi-energy complementary uncertainty scheduling method is proposed to address these issues and ensure a stable power supply from NPS to cloud computing centers. First, we constructed a stochastic differential equation (SDE) to represent the uncertainty characteristics of renewable energy generation, and proposed a SDE deep network based on LSTM (LSTM-SDE Net) to capture and learn the aleatoric uncertainty and epistemic uncertainty of units; subsequently, we established the multi-energy complementary uncertain many-objective scheduling model (MuC-UMaOSM) by utilizing the interval parametric estimation, which aims to optimize grid total cost (TC), RES consumption rate (CR), CEs, grid economic benefits (EB) and load balancing (LB); finally, in order to obtain trade-off solutions with improved convergence, diversity, and uncertainty, we designed a two-population cooperative interval many-objective evolutionary algorithm (T-PIMaOEA) to solve the proposed model. Experimental results demonstrate the excellent performance of our method in the multi-energy complementary scheduling (MECS).

Summary With the development of the Internet of Things (IoT), the number of terminal devices is rapidly growing and at the same time, their security is facing serious challenges. For the industrial control system, there are challenges in detecting and preventing botnet. Traditional detection methods focus on capturing and reverse analyzing the botnet programs first and then parsing the extracted features from the malicious code or attacks. However, their accuracy is very low and their latency is relatively high. Moreover, they sometimes even cannot recognize the unknown botnets. The machine learning based detection methods rely on manual feature engineering and have a weak generalization. The deep learning‐based methods mostly rely on the system log, which does not take into account the multisource information such as traffic. To address the above issues, from the perspective of the botnet features, this paper proposes an intelligent detection method over parallel CNN‐LSTM, integrating the spatial and temporal features to identify botnets. Experimental demonstrate that the accuracy, recall, and F1‐score of our proposed method achieve up to over 98%, and the precision, 97.8%, is not the highest but reasonable. It reveals compared with the existing start‐of‐the‐art methods, our proposed method outperforms in the botnet detection. Our methodology's strength lies in its ability to harness the multifaceted information present in IoT traffic, offering a more nuanced and comprehensive analysis. The parallel CNN‐LSTM architecture ensures that spatial and temporal data are processed concurrently, preserving the integrity of the information and enabling a more robust detection mechanism. The result is a detection system that not only performs exceptionally well in a controlled environment but also holds promise for real‐world application, where the rapid and accurate identification of botnets is paramount.

Abstract As a crucial factor, population diversity greatly affects performances of swarm intelligence algorithms. Especially, for large‐scale optimization problems (LSOPs), the searching space is huge and the number of local optima dramatically increases. Hence to well address LSOPs, a healthy population diversity is helpful to prevent a swarm from premature convergence. However, this is a big challenge to balance exploration and exploitation for swarm intelligence algorithms. To handle with this issue, in this paper, we design a novel algorithm structure for swarm update. In the proposed algorithm, a swarm is divided into several groups and conduct competition in each group where the loser will learn from the winner and meanwhile the winner does nothing in the corresponding iteration. For diversity measurement, we abandon the distance‐based measurement, but employ a frequency‐based measurement, namely entropy indicator, so that the diversity maintenance can be conducted with a different measurement of convergence situation. In this way, the diversity maintenance and convergence can be conducted simultaneously and independently. The benchmarks on the suite of LSOPs are employed to validate the performance of a proposed algorithm. By comparing several state‐of‐the‐art competitor algorithms, the results demonstrate that the proposed algorithm is effective and competitive in dealing with LSOPs.

Summary It is difficult to protect users' privacy and to process private information due to the complexity and uncertainty of such information. To protect private information quickly and accurately, a many‐objective optimization algorithm framework based on the hybrid elite selection strategy is proposed in this paper. First, a mating selection mechanism combined with the achievement scale function and angle information index is used to generate elite offspring of the internal population. Then, the balanceable fitness estimation method is employed to select and update the external archive. To test performance, the proposed algorithm is tested on many‐objective optimization problems (MaOPs) and compared with five state‐of‐the‐art algorithms. Experimental simulation results show that the proposed algorithm is more effective in solving MaOPs and can inspire development of a better privacy protection strategy.